A Python SDK for agents that work together
An agent is a model, a set of instructions, and the tools it may call. A network is several of them behind a router that decides which one gets the turn. Both are a few lines.
Open source, MIT. pip install hanzo-agent. Works against any endpoint that speaks the Chat Completions format, so it runs on Hanzo or on your own serving stack.
One agent, or several with a router between them
The hard part of multi-agent work is not the prompting. It is deciding who answers, keeping what they learn where the next one can read it, and being able to see afterwards what actually ran.
Agents
Agent(name, instructions, tools=[...]) and Runner.run_sync(agent, "…"). The result carries final_output plus every step it took to get there.
Networks
create_network(agents=[researcher, writer], router=SemanticRouter()) puts specialists behind one call. Route on meaning, on rules you write, or by load — and swap the router without touching the agents.
Tools
A tool is a Python function with a signature. Every Hanzo MCP tool is one too, so an agent gets a shell, a filesystem, a code index and HTTP without you writing wrappers for them.
The parts you would otherwise write yourself
Routing you can choose
SemanticRouter reads the request and picks. Rule-based routing does what you say. Load-balanced routing spreads turns across equals. Same network object either way.
Workflows, not just chat
Steps that run in parallel, branch on a condition, or loop until something holds — for the work where the order matters and a prompt cannot express it.
Shared state
Agents in a network read and write one state object, so the writer sees what the researcher found without you pasting it into the next prompt.
Memory with retrieval
A store, a retriever, and vector search over both, so an agent recalls the relevant part of a long history instead of replaying all of it.
Tracing
Spans and traces around every model call, tool call and handoff, through a processor interface you can point at your own collector.
Extras you opt into
pip install "hanzo-agent[tee]" adds attestation for confidential runs. [web3] adds wallets and on-chain identity. [cli] adds the command line. Nothing you skip is loaded.
Two agents and a router
pip install hanzo-agent
from agents import Agent
from agents.network import create_network, SemanticRouter
researcher = Agent(
name="Researcher",
instructions="You find and analyze information.",
tools=[search_tool, analyze_tool],
)
writer = Agent(
name="Writer",
instructions="You create content based on research.",
tools=[format_tool],
)
network = create_network(agents=[researcher, writer], router=SemanticRouter())
result = await network.run("Research and write about quantum computing")Write the first one
pip install hanzo-agent, give it instructions and a tool, and run it.